© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64292
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ('^
    -0.26
    å°¼
    -0.25
    è£ħ
    -0.24
    ?"↵↵↵↵
    -0.24
    ót
    -0.24
    yal
    -0.23
    second
    -0.23
     Marin
    -0.23
     Hers
    -0.23
    umba
    -0.23
    POSITIVE LOGITS
    theses
    0.34
    çģ¯
    0.31
    ocks
    0.27
    leases
    0.26
    `s
    0.25
    åıĸå¾Ĺ
    0.24
     erh
    0.24
    ments
    0.24
    á»ĩu
    0.23
     lhs
    0.23
    Activations Density 5.887%

    No Known Activations

    This feature has no known activations.